In machine learning, to improve something you often need to be able to measure it. TensorBoard is a tool for providing the measurements and visualizations needed during the machine learning workflow. It enables tracking experiment metrics like loss and accuracy, visualizing the model graph, projecting NLP embeddings to a lower-dimensional space, and much more.
TensorBoard provides the following functionalities:
- Visualizing different metrics such as loss, accuracy with the help of different plots, and histograms.
- Visualize model layers and operations with the help of graphs.
- Provide histograms for weights and biases involved in training.
- Displaying training data (image, audio, and text data).
TensorBoard has the following tabs:
- Scalars: This tab is used to visualize the scalar metrics such as loss and accuracy.
- Graph: Visualize the computational graph of your models, such as the neural network model in the form layers and operations.
- Distributions: Visualize the training progression over time such as weight/bias changes.
- Histogram: Visualize the above distribution in the form of 3D-histograms.
- Projectors: This tab is used to visualize the word embedding for Natural Language Processing.
- Images: This tab is used to visualize the contents of training/test images data.
- Audio: This tab is used to visualize the audio data for application such as audio processing
- Text: This tab is used to visualize the audio data.
Implementation :
- Load TensorBoard extension:
Code:
python3
# Install it using pip!pip install -q tf-nightly-2.0-preview# To load tensorflow extensionimport tensorflow as tfimport datetime, os# location of log directorylogs_base_dir = "./logs"os.makedirs(logs_base_dir, exist_ok=True)%tensorboard --logdir {logs_base_dir} |
- Plot Training Images:
Code:
python3
# Import necessary modulesimport numpy as npimport matplotlib.pyplot as pltimport io# Copy previous logs if any!rm -rf ./logs/# Load datasets (Here,we use cifar 10cifar_10 = tf.keras.datasets.cifar10(x_train, y_train), (x_test,y_test) = cifar_10.load_data()# List class Namesclass_names =["airplane","automobile","bird","cat","deer", "dog","frog","horse", "ship","truck"]# Data Preprocessingx_train = x_train.astype('float32')x_test = x_test.astype('float32')x_train = x_train/255.0x_test = x_test/255.0y_train = tf.keras.utils.to_categorical(y_train)y_test = tf.keras.utils.to_categorical(y_test)# Creates a directory inside log/train_data folder# In which we store training imageslogdir = "logs/train_data/" + datetime.now().strftime("%Y%m%d-%H%M%S")# Creates a file writer for the log directory.file_writer = tf.summary.create_file_writer(logdir)# write first 25 training imageswith file_writer.as_default(): # Reshape the images because tf.summary expects a 4 dimensional matrices # having (batch_size,height, width, color_channels) images = np.reshape(x_train[0:25], (-1, 32, 32, 3)) tf.summary.image("Display training data", images, max_outputs=25, step=0)# start TensorBoard and display those images (in images tab)%tensorboard --logdir logs/train_data |
Training Images
- Plot Images Data Using Matplotlib: We can see that the above training images are not clear. That’s because the above training images are of size (32, 32, 3) which is of very low resolution. Let’s plot some images in matplotlib.
Code:
python3
# remove old plots data (if any)!rm -rf logs/plotslogdir = "logs/plots/" + datetime.now().strftime("%Y%m%d-%H%M%S")file_writer = tf.summary.create_file_writer(logdir)def plot_to_image(figure): """Converts the matplotlib plot to a PNG image and returns it. The supplied figure is closed and inaccessible after this call.""" # Save the plot to a PNG in memory. buf = io.BytesIO() plt.savefig(buf, format='png') # Closing the figure prevents it from being displayed directly inside # the notebook. plt.close(figure) buf.seek(0) # Convert PNG buffer to TF image image = tf.image.decode_png(buf.getvalue(), channels=4) # Add the batch dimension print(image.shape) image = tf.expand_dims(image, 0) return imagedef image_grid(): """Return a 5x5 grid of the training images as a matplotlib figure.""" # Create a figure to contain the plot. figure = plt.figure(figsize=(10,10)) for i in range(25): # create the next subplot with class name as its title plt.subplot(5, 5, i + 1, title = class_names[np.int(np.where(y_train[i] ==1)[0])]) plt.xticks([]) plt.yticks([]) plt.grid(False) plt.imshow(x_train[i]) return figure# Prepare the plotfigure = image_grid()# Convert to image and logwith file_writer.as_default(): tf.summary.image("Training data", plot_to_image(figure), step=0)# start tensorboard and display plot%tensorboard --logdir logs/plots |
Training Images using matplotlib
- Display Training Results Metrics: In this section, we will be plotting results metrics on TensorBoard. We will be using scalars and images tabs to display our results. For that, we will define a Convolutional Neural Network model and train it on CIFAR 10 dataset for 20 epoch.
Code:
python3
# Define CNN modelmodel = tf.keras.models.Sequential([ tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=(32, 32, 3)), tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'), tf.keras.layers.MaxPooling2D((2, 2)), tf.keras.layers.Dropout(0.2), tf.keras.layers.Conv2D(64, (3, 3), activation='relu', padding='same'), tf.keras.layers.Conv2D(64, (3, 3), activation='relu', padding='same'), tf.keras.layers.MaxPooling2D((2, 2)), tf.keras.layers.Dropout(0.2), tf.keras.layers.Flatten(), tf.keras.layers.Dense(64, activation='relu'), tf.keras.layers.Dense(10, activation='softmax')])# Compile CNN modelmodel.compile( optimizer=tf.keras.optimizers.SGD(learning_rate= 0.01 , momentum=0.1), loss='categorical_crossentropy', metrics=['accuracy'])# Print model summary()model.summary() |
Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= conv2d (Conv2D) (None, 32, 32, 32) 896 _________________________________________________________________ conv2d_1 (Conv2D) (None, 32, 32, 32) 9248 _________________________________________________________________ max_pooling2d (MaxPooling2D) (None, 16, 16, 32) 0 _________________________________________________________________ dropout (Dropout) (None, 16, 16, 32) 0 _________________________________________________________________ conv2d_2 (Conv2D) (None, 16, 16, 64) 18496 _________________________________________________________________ conv2d_3 (Conv2D) (None, 16, 16, 64) 36928 _________________________________________________________________ max_pooling2d_1 (MaxPooling2 (None, 8, 8, 64) 0 _________________________________________________________________ dropout_1 (Dropout) (None, 8, 8, 64) 0 _________________________________________________________________ flatten (Flatten) (None, 4096) 0 _________________________________________________________________ dense (Dense) (None, 64) 262208 _________________________________________________________________ dense_1 (Dense) (None, 10) 650 ================================================================= Total params: 328,426 Trainable params: 328,426 Non-trainable params: 0 _________________________________________________________________
- Now, we define the function to plot the confusion matrix using test data
Code:
python3
# Code to plot confusion matrixdef plot_confusion_matrix(cm, class_names): """ Returns a matplotlib figure containing the plotted confusion matrix. Args: cm (array, shape = [n, n]): a confusion matrix of integer classes class_names (array, shape = [n]): String names of the integer classes """ figure = plt.figure(figsize=(8, 8)) plt.imshow(cm, interpolation='nearest', cmap=plt.cm.Blues) plt.title("Confusion matrix") plt.colorbar() tick_marks = np.arange(len(class_names)) plt.xticks(tick_marks, class_names, rotation=45) plt.yticks(tick_marks, class_names) # Normalize the confusion matrix. cm = np.around(cm.astype('float') / cm.sum(axis=1)[:, np.newaxis], decimals=2) # Use white text if squares are dark; otherwise black. threshold = cm.max() / 2. for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])): color = "white" if cm[i, j] > threshold else "black" plt.text(j, i, cm[i, j], horizontalalignment="center", color=color) plt.tight_layout() plt.ylabel('True label') plt.xlabel('Predicted label') return figure |
- Now, we define the TensorBoard callback to display the confusion matrix of the model predictions over test data.
Code:
python3
logdir = "logs/image/" + datetime.now().strftime("%Y%m%d-%H%M%S")# Define the basic TensorBoard callback.tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=logdir)# Create file Writer for Confusion Metricsfile_writer_cm = tf.summary.create_file_writer(logdir + '/cm') |
- Now, we define the function to log the confusion matrix into the Tensorboard.
Code:
python3
# sklearn confusion metricsfrom sklearn.metrics import confusion_matriximport itertoolsdef log_confusion_matrix(epoch, logs): # Use the model to predict the values from the validation dataset. test_pred_raw = model.predict(x_test) test_pred = np.argmax(test_pred_raw, axis=1) y_test_cls = np.argmax(y_test, axis=1) # Calculate the confusion matrix. cm = confusion_matrix(y_test_cls, test_pred) figure = plot_confusion_matrix(cm, class_names=class_names) cm_image = plot_to_image(figure) # Log the confusion matrix as an image summary. with file_writer_cm.as_default(): tf.summary.image("Confusion Matrix", cm_image, step=epoch)# Define the per-epoch callback to plot confusion metrics after each epoch.cm_callback = tf.keras.callbacks.LambdaCallback(on_epoch_end=log_confusion_matrix) |
Code:
python3
%tensorboard --logdir logs/image# Train the classifier.model.fit( x_train, y_train, epochs=20, callbacks=[tensorboard_callback, cm_callback], validation_data=(x_test, y_test)) |
Loss & Accuracy Graph (Scalar Tab)
Keras Model Graph (Graph Tab)
Confusion Matrix (Images Tab)
References:
